GPU Offloading: The Next Chapter for Intel® Fortran Compiler
GPU Offloading: The Next Chapter for Intel® Fortran Compiler
Subscribe Now
Stay in the know on all things CODE. Updates are delivered to your inbox.
Overview
Launched in December 2003, Intel® Fortran Compilers are pushing 20 years of global support for Windows*, Linux*, and macOS* in generating code for IA-32 and IA-64 processor architectures.
This session focuses on the progress and features of the latest Intel Fortran Compiler, which is based on LLVM*. This compiler supports oneAPI and OpenMP* offload to Intel GPUs, including 4th generation Intel® Xeon® Scalable processors and Intel® Data Center GPUs.
Hear the development team for Intel Fortran Compiler share their progress for the new compiler, including:
- Achieving full Fortran 2018 language support, putting it on par with Intel® Fortran Compiler Classic.
- Supporting Fortran standards.
- Understanding the compiler's automatic offload of DO_CONCURRENT.
- Exploring how to use the compiler's support for OpenMP offload on GPUs.
Skill level: All
Featured Software
Get the Intel Fortran Compiler as part of the Intel® HPC Toolkit or get it as a stand-alone version.
Deliver fast applications that scale across clusters with tools and libraries for vectorization, multi-node parallelization, memory optimization, and more.